MF-PAM: Accurate Pitch Estimation through Periodicity Analysis and Multi-level Feature Fusion
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916943553888256 |
|---|---|
| author | Chung, Woo-Jin Kim, Doyeon Chung, Soo-Whan Kang, Hong-Goo |
| author_facet | Chung, Woo-Jin Kim, Doyeon Chung, Soo-Whan Kang, Hong-Goo |
| contents | We introduce Multi-level feature Fusion-based Periodicity Analysis Model (MF-PAM), a novel deep learning-based pitch estimation model that accurately estimates pitch trajectory in noisy and reverberant acoustic environments. Our model leverages the periodic characteristics of audio signals and involves two key steps: extracting pitch periodicity using periodic non-periodic convolution (PNP-Conv) blocks and estimating pitch by aggregating multi-level features using a modified bi-directional feature pyramid network (BiFPN). We evaluate our model on speech and music datasets and achieve superior pitch estimation performance compared to state-of-the-art baselines while using fewer model parameters. Our model achieves 99.20 % accuracy in pitch estimation on a clean musical dataset. Overall, our proposed model provides a promising solution for accurate pitch estimation in challenging acoustic environments and has potential applications in audio signal processing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_09640 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | MF-PAM: Accurate Pitch Estimation through Periodicity Analysis and Multi-level Feature Fusion Chung, Woo-Jin Kim, Doyeon Chung, Soo-Whan Kang, Hong-Goo Audio and Speech Processing We introduce Multi-level feature Fusion-based Periodicity Analysis Model (MF-PAM), a novel deep learning-based pitch estimation model that accurately estimates pitch trajectory in noisy and reverberant acoustic environments. Our model leverages the periodic characteristics of audio signals and involves two key steps: extracting pitch periodicity using periodic non-periodic convolution (PNP-Conv) blocks and estimating pitch by aggregating multi-level features using a modified bi-directional feature pyramid network (BiFPN). We evaluate our model on speech and music datasets and achieve superior pitch estimation performance compared to state-of-the-art baselines while using fewer model parameters. Our model achieves 99.20 % accuracy in pitch estimation on a clean musical dataset. Overall, our proposed model provides a promising solution for accurate pitch estimation in challenging acoustic environments and has potential applications in audio signal processing. |
| title | MF-PAM: Accurate Pitch Estimation through Periodicity Analysis and Multi-level Feature Fusion |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2306.09640 |